llama.cppvsUmami
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| llama.cpp | Umami | |
|---|---|---|
| Score | 93/100 | 85/100 |
| Rank in category | #2 of 25 in LLM Inference | #1 of 21 in Web analytics |
| GitHub stars | 132 674 | 39 757 |
| Stars, last 30 days | +3 317 | +776 |
| Stable releases, 12 months | 1461 | 13 |
| Latest release | b11972 · 28 Oct 2026 | v3.4.1 · 23 Oct 2026 |
| Setup | Moderate | Easy |
| Official Docker image | Yes | Yes |
| License | MIT | MIT |
| Main language | C++ | Typescript |
Which one should you pick?
llama.cpp scores 93/100 against 85/100 for Umami, so it is the safer default.
llama.cpp ships more often: 1461 stable releases in the past year, against 13 for Umami.
If you want the quickest setup, Umami is easier to run; llama.cpp needs more configuration.
llama.cpp is growing faster right now (+3 317 stars in 30 days).
llama.cpp details →Umami details →